Efficient Training of Energy-Based Models Using Jarzynski Equality

arXiv2305.19414MaRDI QIDQ6438573

Author name not available (Why is that?)

Publication date: 30 May 2023

Abstract: Energy-based models (EBMs) are generative models inspired by statistical physics with a wide range of applications in unsupervised learning. Their performance is best measured by the cross-entropy (CE) of the model distribution relative to the data distribution. Using the CE as the objective for training is however challenging because the computation of its gradient with respect to the model parameters requires sampling the model distribution. Here we show how results for nonequilibrium thermodynamics based on Jarzynski equality together with tools from sequential Monte-Carlo sampling can be used to perform this computation efficiently and avoid the uncontrolled approximations made using the standard contrastive divergence algorithm. Specifically, we introduce a modification of the unadjusted Langevin algorithm (ULA) in which each walker acquires a weight that enables the estimation of the gradient of the cross-entropy at any step during GD, thereby bypassing sampling biases induced by slow mixing of ULA. We illustrate these results with numerical experiments on Gaussian mixture distributions as well as the MNIST dataset. We show that the proposed approach outperforms methods based on the contrastive divergence algorithm in all the considered situations.

Has companion code repository: https://github.com/submissionx12/ebms_jarzynski

This page was built for publication: Efficient Training of Energy-Based Models Using Jarzynski Equality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6438573)